© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 18780
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to entertainment, such as names of movies, TV shows, and games

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote the creation or production of various media, particularly those stating "was."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dialogue
    -0.71
    ARE
    -0.64
    arta
    -0.62
    Relations
    -0.60
    Const
    -0.58
     occupational
    -0.58
     msec
    -0.57
     trusts
    -0.57
    Footnote
    -0.57
     Occupations
    -0.57
    POSITIVE LOGITS
     launched
    1.33
     conceived
    1.32
     unveiled
    1.29
     released
    1.22
     announced
    1.21
     debuted
    1.20
     founded
    1.17
     discontinued
    1.16
     awarded
    1.15
     teased
    1.13
    Activations Density 0.168%

    No Known Activations